Design Considerations for High Impact, Automated Echocardiogram Analysis — Yoni Nachmany

Abstract
Deep learning has the potential to automate echocardiogram analysis for early detection of heart disease. Based on a qualitative analysis of design concerns, this study suggests that predicting normal heart function instead of disease accounts for data quality bias and significantly increases efficiency in cardiologists' workflows.

“Design Considerations for High Impact, Automated Echocardiogram Analysis”: abstract, paper, code

Presented at ICML 2020 Machine Learning for Global Health Workshop

Mitigating Geographic Bias of Image Classifiers with Multilingual Image Data

Learning Word Ratings for Empathy and Distress from Document-Level User Responses